New research on AI and security, selected for relevance to language models, AI agents and cybersecurity. Summaries are the authors’ or publisher’s own words, linked to the original.
Peer-reviewed
Dynamic path reasoning with large language models for interpretable knowledge graph question answering
PhD students who write dissertation with AI less likely to stay in academia
Probabilistic algorithms for Ising machines from optimization to generative AI
Margaret Hamilton obituary: computer scientist who pioneered software engineering and helped us get to the Moon
Dendritic computation bridges neuroscience and foundation models
New preprints (not yet peer-reviewed)
SoK: Trading Agents or Market Crashers? Dissecting Robustness and Security Failures in Academic Financial LLM Trading Schemes
Large language model (LLM) agents already trade with real capital, yet agent-security research has mostly treated them as generic agents. Trading changes the threat: a compromised agent's orders move prices that other participants act on, and an attacker who profits from a crash can trigger the shock that a non-robust agent mishandles.
Why Do Agent Teams Fail Across Boundaries? A Failure Taxonomy for Agent-to-Agent Systems with Private States
Agents are increasingly interacting with other agents that act for different principals (people or organizations on whose behalf they work), such as a buyer's personal agent negotiating with an enterprise's seller agent. In such agent-to-agent (A2A) scenarios, each agent has its own environment and holds information and authority that the other cannot see.
CompMat-Bench: Benchmarking AI Agents for Computational Materials Science
Evaluating AI agents on scientific research tasks is constrained by the time and resources required for the underlying experiments or calculations. In computational materials research, repeating the same expensive simulations across agents and trials can make evaluation impractical.
StepSafe: Learning Timely Intervention with Context-Aware Safety Reasoning
Safety in agentic systems is inherently sequential: whether an action is safe depends on prior actions, tool outputs, information disclosures, and interactions among agents. Recent work has shifted agent safety guardrails from post-hoc trajectory-level assessment toward step-level action diagnosis and proactive risk prediction, yet existing training objectives provide limited supervision for how step evidence accumulates over time and when it becomes sufficient to justify intervention.
INFUSE: A Unified Surface Benchmark for Indirect Prompt Injection in Agentic Systems
LLM-based agents increasingly execute long-horizon, end-to-end workflows involving shell commands, code modification, dependency installation, and interaction with remote services. This growing autonomy expands their exposure to indirect prompt injection (IPI), where adversarial instructions embedded in external content are interpreted as legitimate task directives.
IneqAgent: Agentic Inequality Proving in Lean with Symbolic Computation
Formal inequality proving requires mathematical reasoning and exact computation, often connected through intermediate lemmas and goal reformulations. We introduce IneqAgent, an agentic framework combining LLM reasoning with symbolic computation for inequality proving in Lean4.
Athanor: An Agent-Native System for Autonomous Post-Training Research
Recursive self-improvement, in which AI systems build stronger AI systems, is one promising route to superintelligence. We study a weaker form that can be measured today: frontier agents post-training a small raw base model with public data, as a test of their research potential.
SecureClaw: Clawing Back Control of LLM Agents
Tool-using large language model (LLM) agents face two distinct security failures: unauthorized external actions and exposure of sensitive plaintext inside the runtime before any final output check can intervene. Existing defenses usually protect one boundary, either the planner/runtime or the point where external actions are executed, and therefore do not by themselves secure both surfaces.